Forecasting household electricity demand with hybrid machine learning-based methods: Effects of residents’ psychological preferences and calendar variables
作者：
Highlights：
• Forecast electricity demand considering residents’ psychological preferences.
• Stationarity time series are established to avoid the impact of irregular factors.
• Personalizes exogenous variables, combines correlations and importance.
• A hybrid machine learning based model is built to improve forecasting performance.
• Multiple implications are provided for the government and institutions.
摘要
•Forecast electricity demand considering residents’ psychological preferences.•Stationarity time series are established to avoid the impact of irregular factors.•Personalizes exogenous variables, combines correlations and importance.•A hybrid machine learning based model is built to improve forecasting performance.•Multiple implications are provided for the government and institutions.
论文关键词：Household electricity demand forecasting,Residents’ psychological preferences,Calendar variables,Machine learning,Feature selection
论文评审过程：Received 23 September 2020, Revised 27 March 2021, Accepted 10 June 2022, Available online 13 June 2022, Version of Record 17 June 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117854
